Duboko poticano učenje i njegova primjena u implementaciji umjetnog igrača strateške videoigre

master's thesis

• Title (english): Deep Reinforcement Learning with Application to Artificial Strategy Video Game Player Implementation
• Author: Leon Hrid Hinić
• Mentor: Bogdan Okreša Đurić (mentor); MBZ: 367114
• Committee member: Markus Schatten (član povjerenstva); MBZ: 291806
• Granter: University of Zagreb; Faculty of Organization and Informatics; (Department of Theoretical and Applied Foundations of Information Sciences); Varaždin
• Defense date and country: 2024-02-02, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

Osnova rada je koncept dubokog poticanog učenja, pristupa implementacije strojnog učenja koji kombinira elemente poticanog i dubokog strojnog učenja, te njegovu primjenu u domeni video igara. Praktični dio rada obuhvaća implementiranje umjetnog inteligentnog igrača strateške videoigre koji koristi samostalno razvijen model dubokog poticanog učenja.

• Keywords: umjetna inteligencija; duboko učenje; reinforcement learning; videoigre; poticano učenje
• Language: croatian
• URN:NBN: urn:nbn:hr:211:269887
• Study programme: Title: Database and Knowledge Base Studies; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informatike (magistar/magistra informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-02-05 05:00:46